Remaining useful life prediction considering degradation interactions of subsea Christmas tree: A multi-stage modeling approach

Interactions exist in the performance degradation of the systems because of uneven distribution of working pressures of components. Actually, even the same two components have different degradation processes under the natural degradation or external impact. For a complex system, even if single degradation process of com-ponents is known, it is still difficult to evaluate its overall performance. The remaining useful life (RUL) of the system is also tough to estimate due to the effects of interactions. This paper contributed a multi-stage model -based RUL estimation approach considering interactions. The framework of the approach is based on Bayesian networks (BNs). On the one hand, BNs is used to identify and match the system degradation stage, and on the other hand, it is used to deal with the uncertainty of parameters in the RUL estimation. Multi-stage degradation and interaction coefficients are the two most important tasks to complete the RUL estimation considering in-teractions. The RUL are obtained from the time difference from healthy operation to failure. An electro-hydraulic subsea Christmas tree is adopted to demonstrate the proposed approach. The results show that the approach can effectively evaluate the system performance and RUL under the influence of interactions.

Automated summary

The uneven distribution of working pressures in components leads to interactions in system performance degradation. Even the same two components have different degradation processes due to natural degradation or external impact. This paper proposes a multi-stage model-based RUL estimation approach using Bayesian networks, which can effectively evaluate system performance and RUL considering interactions.